Update app.py

app.py

@@ -1,82 +1,32 @@
-import gradio as gr
-
-def greet(name):
-    return "Hello " + name + "!!"
-
-
-
-
-
-# Import pandas
+import streamlit as st
 import pandas as pd
-
-# Use pandas to read in recent_grads_url
-recent_grads = pd.read_csv("/content/recent_grads.csv")
-
-# Print the shape
-print(recent_grads.shape)
-
-from google.colab import drive
-drive.mount('/content/drive')
-
-# Print .dtypes
-print(recent_grads.dtypes)
-
-# Output summary statistics
-print(recent_grads.describe())
-
-# Exclude data of type object
-print(recent_grads.describe(exclude=["object"]))
-
-# Names of the columns we're searching for missing values
-columns = ['median', 'p25th', 'p75th']
-
-# Take a look at the dtypes
-print(recent_grads[columns].dtypes)
-
-# Find how missing values are represented
-print(recent_grads["median"].unique())
-
-# Replace missing values with NaN
-for column in columns:
-    recent_grads.loc[recent_grads[column] == 'UN', column] = np.nan
-
 import numpy as np
-import pandas as pd
 
-# Assuming 'recent_grads' is your DataFrame and 'columns' is a list of columns needing correction
+# Function to load data and replace missing values
+@st.cache
+def load_data():
+    # Load your data here, assuming 'recent_grads' is your DataFrame
+    # Replace 'your_data.csv' with your actual data file
+    recent_grads = pd.read_csv('your_data.csv')
 
-# Replace missing values with NaN
-for column in columns:
-    recent_grads.loc[recent_grads[column] == 'UN', column] = np.nan
+    # List of columns needing correction
+    columns_to_correct = ['column1', 'column2', 'column3']  # Replace these with your columns
 
-# Select sharewomen column
-sw_col = recent_grads['sharewomen']
+    # Replace 'UN' with NaN in specified columns
+    for column in columns_to_correct:
+        recent_grads.loc[recent_grads[column] == 'UN', column] = np.nan
 
-# Output first five rows
-print(sw_col.head())
+    return recent_grads
 
-# Import numpy
-import numpy as np
-
-# Use max to output maximum values
-max_sw = recent_grads['sharewomen'].max()
-
-# Print column max
-print(max_sw)
-
-# Output the row containing the maximum percentage of women
-#print(sw_col)
-print(recent_grads[(recent_grads['sharewomen']==max_sw)])
-
-# Convert to numpy array
-import numpy as np
-recent_grads_np=np.array(recent_grads[['unemployed', 'low_wage_jobs']])
+def main():
+    st.title('Data Handling with Streamlit')
 
+    # Load data
+    data = load_data()
 
-# Print the type of recent_grads_np
-print(type(recent_grads_np))
+    # Show the loaded data in Streamlit
+    st.write("Original Data:")
+    st.write(data)
 
-print(np.corrcoef(recent_grads_np[:,0], recent_grads_np[:,1]))
-iface = gr.Interface(fn=greet, inputs="text", outputs=recent_grads[(recent_grads['sharewomen']==max_sw])
-iface.launch()
+if __name__ == "__main__":
+    main()